Utilizing convolutional neural networks to extract road features from Swiss historical maps

This paper introduces a methodology to support network managers in the quantification of the risk related to their networks. The method emphasizes the integration of the spatial and temporal attributes of the events that need to be modeled to estimate the risk. This work then demonstrates the usefulness of the methodology through its application to design and implement a risk assessment to estimate the potential impact of flood and mudflow events on a road network located in Switzerland.